Xiaoyu Chu

Sha Yuan, Hanyu Zhao, Shuai Zhao et al. · bytedance, pku

With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm. Researchers have achieved various outcomes in the construction of BMs and the BM application in many fields. At present, there is a lack of research work that sorts out the overall progress of BMs and guides the follow-up research. In this paper, we cover not only the BM technologies themselves but also the prerequisites for BM training and applications with BMs, dividing the BM review into four parts: Resource, Models, Key Technologies and Application. We introduce 16 specific BM-related topics in those four parts, they are Data, Knowledge, Computing System, Parallel Training System, Language Model, Vision Model, Multi-modal Model, Theory&Interpretability, Commonsense Reasoning, Reliability&Security, Governance, Evaluation, Machine Translation, Text Generation, Dialogue and Protein Research. In each topic, we summarize clearly the current studies and propose some future research directions. At the end of this paper, we conclude the further development of BMs in a more general view.

Xiaoyu Chu, Shashikant Ilager, Yizhen Zang et al.

Incident management is essential to maintain the reliability and availability of cloud computing services. Cloud vendors typically disclose incident reports to the public, summarizing the failures and recovery process to help minimize their impact. However, such reports are often lengthy and unstructured, making them difficult to understand, analyze, and use for long-term dependability improvements. The emergence of LLMs offers new opportunities to address this challenge, but how to achieve this is currently understudied. In this paper, we explore the use of cutting-edge LLMs to extract key information from unstructured cloud incident reports. First, we collect more than 3,000 incident reports from 3 leading cloud service providers (AWS, AZURE, and GCP), and manually annotate these collected samples. Then, we design and compare 6 prompt strategies to extract and classify different types of information. We consider 6~LLM models, including 3 lightweight and 3 state-of-the-art (SotA), and evaluate model accuracy, latency, and token cost across datasets, models, prompts, and extracted fields. Our study has uncovered the following key findings: (1) LLMs achieve high metadata extraction accuracy, $75\%\text{--}95\%$ depending on the dataset. (2) Few-shot prompting generally improves accuracy for meta-data fields except for classification, and has better (lower) latency due to shorter output-tokens but requires $1.5\text{--}2\times$ more input-tokens. (3) Lightweight models (e.g., Gemini~2.0, GPT~3.5) offer favorable trade-offs in accuracy, cost, and latency; SotA models yield higher accuracy at significantly greater cost and latency. Our study provides tools, methodologies, and insights for leveraging LLMs to accurately and efficiently extract incident-report information. The FAIR data and code are publicly available at https://github.com/atlarge-research/llm-cloud-incident-extraction.

Shekhar Suman, Xiaoyu Chu, Alexandru Iosup

By 2025, there are zettabytes of data generated every year. The size and complexity of modern large-scale computing infrastructures like High-Performance Computing (HPC) systems continue to evolve and become complex, leaving us wondering about their manageability and sustainability concerns. Because of this reason, those complex systems are provided with fine-grained monitoring and Operational Data Analytics (ODA) capabilities to optimise their efficiency. In this literature study, we list the fundamental pillars of the large-scale computing infrastructures which enable its ODA capabilities, and conduct a study of the popular ODA frameworks operating in various such environments (predominantly HPC). Based on that, we propose a more holistic ODA framework matching the various layers of a large-scale graph-processing distributed ecosystem proposed by Sherif Sak et al, that extends the ODA functionalities presented in an existing novel ODA framework proposed by Netti et al. We compare the holistic ODA framework proposed by us to some of the state-of-the-art frameworks that we study as part of this literature to highlight the novelty, which would hopefully draw more attention to perform extensive research in this field. As part of creating awareness, we highlight the significant operational efficiencies observed as a result of the implementation of the state-of-the-art ODA frameworks to make the study appear beneficial for the readers, and lastly, discuss the trending research work ongoing in this field.